Trying to have a discussion with people who aren't actually interested in being convinced is exhausting. Simon has a lot more patience than I do.

Another lens is that many people either have terrible written communication skills, do not intuitively grasp how to describe a complex system design, or both. And yet, since everyone is a genius with 100% comprehensibility in their own mind, they simply aren't aware that the problem starts with them.

Well I think it also has to do with communication with LLMs being different to communication with humans. If you tell a developer "don't do busywork" they surely wouldn't say "Oh the repo looks like a trash dump, but no busywork so I'm not going to clean it up, quickly document that as canonical structure, then continue"

> have terrible written communication skills

More and more I think this is it.

Can you actually provide any proof, even top-line stats from GitHub or other software forges that show the productivity boost you’re claiming?

It’s not up to the skeptics to prove this tech doesn’t work, it’s up to the proponents to show it does and does so with a similar effect size as cigarettes cause lung cancer.

There are a tremendous amount of LLM productivity stans on HN but the plural of anecdote is not data.

Certainly these tools are useful, but the extent to which they are useful today is not nearly as open and shut as you and others would claim. I’d say that these tools make me 5% more productive on a code base I know well.

I’m totally open to opposing evidence that isn’t just anecdote

I think it’s pretty obvious that is the OP automates this manual part of their workflow that it will improve their iteration speed. The thread root is just saying stop copy and pasting and use the built in tooling to communicate with the LLM apis

"it doesn't make sense" is an odd statement to make for choosing Claude Code vs Cursor.

Would you be willing to go into more detail about that claim?

Happy to!

CC seems best suited to situations where one or both of the following are true:

- presence of CI infrastructure

- the ability for the agent to run/test outputs from the run loop

If you're primarily working on embedded hardware, human-in-the-loop is not optional. In real terms, I am the CI infrastructure.

Also, working on hardware means that I am often discussing the circuit with the LLM in a much more collaborative way than what most folks seem to do with CC requirements. There are MCP servers for KiCAD but they don't seem to do more than integrate with BOM management. The LLMs understand EE better than many engineers do, but they can only understand my circuit (and the decisions embedded in it) as well as I can explain/screencap it to them.

The SDK and tooling for the MCUs also just makes an IDE with extensions a much more ergonomic fit than trying to do everything through CLI command switches.

BTW: it's a statement, not a claim.

The framing of your question as though I might possibly be hallucinating my own situation might be correlated to your lack of reply.

AFAIK, all statements are claims.

I didn't reply because I haven't had available energy to properly analyze your reply. At a glance, your reply does seem completely reasonable, which is why I upvoted it.

Isn't Claude Code the same as Cursor agent mode? I really don't get why anyone would want to lock yourself to one LLM creator in the former vs having all the LLMs in the latter. How do you stop yourself from bursting through the quota with Opus? That's my biggest worry and it keeps me from using it over Sonnet in my Cursor.

Honestly, it depends on what you mean by "the same as". Both are (in my case, at least) running Opus 4.5 instances. After that, it's like using a CNC or a shop full of hand tools. They are both great, and people who know one often know both. The process is wildly different, however.

Not busting my quota is simply not my top priority. I'm on their $200/month plan and I have it locked to a $1000/month overage limit, though the most I've ever gone through using it every day, all day is about $700. That probably sounds like a lot if you're optimizing for a $20/month token budget, but it's budgeted for. That $10-12k/year is excellent value for the silly amount of functionality that I've been able to create.

Sonnet is a really good LLM, and you can build great things with it. However, if you're using this for serious work, IMO you probably want to use the most productive tools available.

Opus 4.1 was, to be real, punishingly expensive. It made me sweat. Thank goodness that Opus 4.5 is somehow both much better and much cheaper.

What do you see as the difference between Claude Code and Cursor agent mode, since you said Claude Code doesn't work for your type of project so I'm curious why that is.

Edit, I see you answered this in another response, thanks.

While I am vaguely aware that CC has started to move past its CLI-first roots, I still think of it as a process that you do in a terminal window vs something you do in an IDE like VSCode or Cursor.

I don't have any interest in yucking anyone's yum, but for me, I find working in and IDE to be vastly more productive than trying to remember dozens of vim and tmux shortcuts.

Claude Code has a Cursor and VSCode extension so it replaces their chat sidebars, which is how many people use it today over just the CLI. What I'm trying to understand is how they're different if so, but it seems like what I'm learning is that they're basically converging in functionality and commoditizing for now and it comes down to personal preference. Personally I still use Cursor because it has a lot of other models than just Claude ones, but I guess some people trust Anthropic enough to not want any other models that may arise in the future too.

Yep, that's exactly what I meant when I said that CC is moving past it's CLI-first roots.

I haven't personally tried the CC extension because like you, I concluded that it sounds like a single-company Cursor with way fewer points of integration into the IDE.

I hate bikeshedding and rarely do I switch tooling unless something is demonstrably better; preferably 10x better. For me, the Cursor IDE experience is easily 10x better than copying and pasting from ChatGPT, which is why I created this thread in the first place.

I have learned more - not just about my daily driver languages, but about other languages I wouldn't have even cracked the seal on, as well as layers of hardware and maker skills - in the past two years than I did in the 30 years leading up to them.

I truly don't understand how anyone creative wouldn't find their productivity soar using these tools. If computers are bicycles for the mind, LLMs are powered exoskeletons with neural-controlled turret cannons.

To extend the metaphor, which provides better exercise for your body? A bicycle or a powered exoskeleton with turret cannons?

I don't bike for exercise. I bike to get where I'm going with the least amount of friction. Different tools for different jobs.

Also: I think we can agree that Ripley was getting a good workout.

In a very real sense, developers efforts to make web development simpler have clearly failed. This is true regardless of the existence of LLMs and/or your opinion of their utility.

They have been very successful. After we got a hit from security requirements and broke the Microsoft monopoly on browsers, web development have only got more and more potentially simple.

If you or some other person don't program in the way that makes it simple, it's not our communitary problem. What matters is that the potential is there.

I think that you are confusing browser engine maturity and developer ecosystem, which means that you're having your own conversation.

You pick the ecosystem you'll use, the only one forced on you is the browser. If you decide to use one that makes your life harder, that's again not a communitary problem.

There’s also change over time to consider: web programming has become immensely more stable and simpler and more mature over time, thereby enabling classes of application and experience that traditionally meant a client application to be built on the web, hence modern web app development becoming a complex and complicated morass.

Facebook and others have delivered a bunch of cross platform shizz that really should be baked into the desktop and mobile OS itself, moving complexity up the stack. Microsoft Office uses React, to highlight the issue. We’ve spent decades chasing the basics of fat client development and doing it in JavaScript.

It's freaking wild that the folks suggesting web development has gotten simpler are also talking about baking React "into the stack" with a straight face.

I don't know what planet y'all are living on, but React is most emblematic of the layers upon layers of BS that people have to deal with today that simply were not an issue 20 years ago.

So you're saying that if you go to any famous restaurant and the famous face of the restaurant isn't personally preparing your dinner with their hands and singular attention, you are disappointed.

Got it.

This approach seems to have worked out for both Warhol and Chihuly.

Can you give some background context for someone reading this and genuinely not knowing what you're referring to?

You absolutely should consume a mixture of news from a variety of reputable sources, mindful of their biases and your own.

I don't love CNN but comparing them to right wing news is pure false equivalency, however.

I don't think that HN leans MAGA, even by a long-shot.

There's lots of folks here that I often disagree with, but even the conservative-leaning tend to be far more willing to at least debate than you'll find on most places on the web.

Honestly, if you truly perceive a MAGA vibe on here, I would stop to question your own notions of what qualifies as moderate.

If you have a “moderate” opinion on this war, I don’t know what to tell you

I didn't express anything of the sort that you're implying, and you don't seem interested in replying to what I said.

If I'm completely honest, I'm not even sure which war you're specifically referring to; I assure you that I'm against all of them.

Every top comment on this thread supports the invasion or hemms and haws at best: https://news.ycombinator.com/item?id=46473348

Sorry for assuming you supported the war [in Venezuela] but I’ve yet to see a moderate that’s anything other than a MAGA whos embarrassed by the asthetic.

Yeah. I'm a life-long Canadian leftist. I think everyone involved in the Trump cabinet should be tried for war crimes.

I also simply do not see even tepid support for this attack in the top comments, to the degree that I seriously wonder if we're looking at the same comments.

I do not want to put words in your mouth, but it really seems as though you're ignoring the fact that multiple things can be true at the same time; Maduro is a sack of shit, the US is demonstrating that they have no interest in the post-WW2 order, and many Venezuelans might be quietly or openly thrilled that he's gone.

But seriously: this is HN. It's a place where people hope to have intelligent conversations and polite debate. I'm not sure what you actually expect people to say which would satisfy your need to see sufficient outrage.

Absolutely nothing about that makes this place slant MAGA. This discussion between us simply wouldn't happen if this place slanted MAGA.

You are stuck on "If is not my brand of liberal, then they are MAGA and worse than Hitler" there is nuance in political opinions; people can be conservative and condemn and disagree with this war/administration/president.

Western society is turning into this tribalistic bullshit, is very visible in ithe US but to my suprise is now also in full force in Canada.

Dang, I'm going to have to leave my Korg OpSix synth at home.

I guess they don't want anyone to jam the GPIO headers into someone's eye.